Being born in autumn or winter is associated with asthma and allergic rhinitis in Finland.

BACKGROUND: Our population-based study has previously shown that being born in winter or spring was associated with adult-onset asthma. The aim was to study if season of birth (SOB) is associated with airway allergy and related diseases: NSAID exacerbated respiratory disease (N-ERD), asthma, allergic rhinitis (AR), nonallergic rhinitis (NAR), chronic rhinosinusitis with nasal polyps (CRSwNP) and CRS without nasal polyps (CRSsNP) in Finland. METHODS: A randomly sampled retrospective registry-based follow-up data (n = 74,868) of patients visiting Hospital District of Helsinki and Uusimaa (HUS) in Finland was used. The birth date, sex, visit date and comorbidities were collected from electronic health record data during visits from 2005 to 2019. RESULTS: The mean (SD, range) age of the sample was 34.53 (25.47, 0-102) years, with 48.7 % being men. We divided the whole population in four groups based on the season they were born (SOB-groups). When observing these four SOB-groups, the proportion of those having asthma was 43.1%, 42.1%, 41.1%, 42.7%, in winter, spring, summer, and autumn SOB-groups, respectively. The proportion of those having AR was 12.6%, 12.0%, 10.7%, 12.1%, respectively. When having summer as a reference, being born in any other time of year was significantly associated with AR and, being born in autumn or winter was associated with asthma. No significant association was observed in CRS or N-ERD or NAR groups in adjusted models. CONCLUSIONS: The study suggests that early life immunological events may have a role a role in pathogenesis of asthma and AR. As no association was observed between SOB and CRSsNP, CRSwNP, N-ERD or NAR, further studies on this are warranted.

Comorbidities of chronic rhinosinusitis in children and adults.

BACKGROUND: Chronic rhinosinusitis (CRS) is a chronic inflammatory disease of the nose and paranasal sinuses lasting ≥12 weeks. CRS may exist with (CRSwNP) or without (CRSsNP) nasal polyps. The aim was to evaluate conditions associated with CRS in a randomized hospital cohort. We hypothesized that comorbidities and surgical procedures differ between pediatric and adult patients. METHODS: This study consisted of hospital registry data of a random sample of rhinosinusitis patients (age range 0-89 years) with the diagnosis of J32 or J33, correspondingly, registered during outpatient visits from 2005 to 2019 (n = 1461). The covariates of interest were collected from electronic health records based on ICD-10 codes and keyword searches. RESULTS: Among pediatric patients (n = 104), the relative proportions of CRSsNP and CRSwNP were 86% and 14% respectively. The relative proportions of adult patients (n = 1357) with CRSsNP and CRSwNP were 60% and 40%, respectively. The following comorbidities significantly differed (p < 0.05) between pediatric and adult populations: allergy, chronic otitis media, and tonsillar diseases. In total, 41 % of the children and 46% of the adults underwent baseline endoscopic sinus surgery (ESS). Additional surgeries of the ear, nose and pharynx were significantly more common among children compared with adults. Risk of revision after baseline ESS was associated (p < 0.05) with allergy, asthma, eosinophilia, CRSwNP, immunodeficiency or its suspicion, non-steroidal anti-inflammatory drug exacerbated respiratory disease, and number of any diseases ≥2. CONCLUSIONS: Our study showed that comorbidities differ between pediatric and adult rhinosinusitis patients, as allergy, asthma and allergy, chronic otitis media, mental health disorders, and tonsils disease were significantly more prevalent among pediatric patients. Children and adults were equally treated with ESS. Notably, children underwent additional surgery on adenoids and tonsils more frequently. The effectiveness of ESS in multimorbid adults should be assessed at an individual level.

Risk factors of NSAID-exacerbated respiratory disease: A population-based study.

BACKGROUND: Asthma with NSAID-exacerbated respiratory disease (NERD) is associated with uncontrolled or severe asthma. NERD patients are more prone to severe allergic reactions and their asthma exacerbations lead to hospitalisations twice as often compared to patients with non-NERD-asthma. NERD patients are prone to recurrent nasal polyposis requiring frequent endoscopic sinus surgeries. However, the early risk factors of NERD are not fully understood. The aim was to identify risk factors of NERD among patients with adult-onset asthma. METHODS: We used data from 1350 population-based adult asthmatics with adult-onset asthma from Finnish national registers. NERD was defined as self-reported wheeze or other typical respiratory symptoms after ingestion of NSAIDs. Thirty-six covariates covering several domains (personal characteristics, life-style, early life factors, asthma characteristics and multimorbidities) were selected based on literature and were studied in association with NERD using logistic regressions. RESULTS: The study population included 153 (11.3%) asthmatics with NERD. Thirty-six covariates were entered in univariate logistic regression analysis, in which 23 were associated with NERD (p < 0.05). These variables were entered in a multivariable logistic regression model in which allergic respiratory symptoms, female sex, osteoarthritis, difficult asthma, nasal polyps, second-hand smoke exposure at home, having 3 or more older siblings and being overweight were significantly associated with asthma with NERD (p < 0.05). Overweight decreased the risk of NERD, other factors increased it. CONCLUSION: According to our study, risk factors of NERD in part are associated with female sex, BMI, exposure to tobacco smoke, allergy, orthopaedic disorders and infection history, and their early recognition might thus be important to manage the burden of NERD.

Trends in cost of treatment of lung cancer patients in 2014-2019 in Finland - a descriptive register study.

AIM: The aim of this descriptive study is to analyze the cost for the treatment of NSCLC and SCLC patients (2014-2019) in Finland. The primary objective is to understand recent (2014-2019) cost developments. METHODS: The study is retrospective and based on hospital register data. The study population consists of NSCLC and SCLC patients diagnosed in four out of the five Finnish university hospitals. The final sample included 4047 NSCLC patients and 766 SCLC patients. RESULTS: Cost of the treatment in lung cancer is increasing. Both the average cost of the first 12 months as well as the first 24 months after diagnosis increases over time. For patients diagnosed in 2014, the average cost of the first 24 months was 19,000 €and for those diagnosed in 2015 22,000 €. The annual increase in the nominal 24-month costs was 10.4% for NSCLC and 7.3% for SCLC patients. CONCLUSION: The average cost per patient has increased annually for both NSCLC and SCLC. Possible explanations to the cost increase are increased medicine costs (especially in NSCLC), and the increased percentage of patients being actively treated.

Personalized Risk Analysis to Improve the Psychological Resilience of Women Undergoing Treatment for Breast Cancer: Development of a Machine Learning-Driven Clinical Decision Support Tool.

BACKGROUND: Health professionals are often faced with the need to identify women at risk of manifesting poor psychological resilience following the diagnosis and treatment of breast cancer. Machine learning algorithms are increasingly used to support clinical decision support (CDS) tools in helping health professionals identify women who are at risk of adverse well-being outcomes and plan customized psychological interventions for women at risk. Clinical flexibility, cross-validated performance accuracy, and model explainability permitting person-specific identification of risk factors are highly desirable features of such tools. OBJECTIVE: This study aimed to develop and cross-validate machine learning models designed to identify breast cancer survivors at risk of poor overall mental health and global quality of life and identify potential targets of personalized psychological interventions according to an extensive set of clinical recommendations. METHODS: A set of 12 alternative models was developed to improve the clinical flexibility of the CDS tool. All models were validated using longitudinal data from a prospective, multicenter clinical pilot at 5 major oncology centers in 4 countries (Italy, Finland, Israel, and Portugal; the Predicting Effective Adaptation to Breast Cancer to Help Women to BOUNCE Back [BOUNCE] project). A total of 706 patients with highly treatable breast cancer were enrolled shortly after diagnosis and before the onset of oncological treatments and were followed up for 18 months. An extensive set of demographic, lifestyle, clinical, psychological, and biological variables measured within 3 months after enrollment served as predictors. Rigorous feature selection isolated key psychological resilience outcomes that could be incorporated into future clinical practice. RESULTS: Balanced random forest classifiers were successful at predicting well-being outcomes, with accuracies ranging between 78% and 82% (for 12-month end points after diagnosis) and between 74% and 83% (for 18-month end points after diagnosis). Explainability and interpretability analyses built on the best-performing models were used to identify potentially modifiable psychological and lifestyle characteristics that, if addressed systematically in the context of personalized psychological interventions, would be most likely to promote resilience for a given patient. CONCLUSIONS: Our results highlight the clinical utility of the BOUNCE modeling approach by focusing on resilience predictors that can be readily available to practicing clinicians at major oncology centers. The BOUNCE CDS tool paves the way for personalized risk assessment methods to identify patients at high risk of adverse well-being outcomes and direct valuable resources toward those most in need of specialized psychological interventions.

Cluster Analysis of Finnish Population-Based Adult-Onset Asthma Patients.

BACKGROUND: Phenotypes of adult asthma have been identified in previous studies but rarely in population-based settings. OBJECTIVE: To identify clusters of adult-onset asthma in a Finnish population-based study on subjects born before 1967. METHODS: We used population-based data from 1350 asthmatics with adult-onset asthma (Adult Asthma in Finland) from Finnish national registers. Twenty-eight covariates were selected based on literature. The number of covariates was reduced by using factor analysis before cluster analysis. RESULTS: Five clusters (CLU1-CLU5) were identified, 3 clusters with late-onset adult asthma (onset ≥40 years) and 2 clusters with onset at earlier adulthood (<40 years). Subjects in CLU1 (n = 666) had late-onset asthma and were nonobese, symptomatic, and predominantly female with few respiratory infections during childhood. CLU2 (n = 36) consisted of subjects who had earlier-onset asthma, were predominantly female, obese with allergic asthma, and had recurrent respiratory infections. Subjects in CLU3 (n = 75) were nonobese, older, and predominantly men with late-onset asthma, smoking history, comorbidities, severe asthma, least allergic diseases, low education, many siblings, and childhood in rural areas. CLU4 (n = 218) was a late-onset cluster consisting of obese females with comorbidities, asthma symptoms, and low education level. Subjects in CLU5 (n = 260) had earlier onset asthma, were nonobese, and predominantly allergic females. CONCLUSIONS: Our population-based adult-onset asthma clusters take into account several critical factors such as obesity and smoking, and identified clusters that partially overlap with clusters identified in clinical settings. Results give us a more profound understanding of adult-onset asthma phenotypes and support personalized management.

Personalized prediction of one-year mental health deterioration using adaptive learning algorithms: a multicenter breast cancer prospective study.

Identifying individual patient characteristics that contribute to long-term mental health deterioration following diagnosis of breast cancer (BC) is critical in clinical practice. The present study employed a supervised machine learning pipeline to address this issue in a subset of data from a prospective, multinational cohort of women diagnosed with stage I-III BC with a curative treatment intention. Patients were classified as displaying stable HADS scores (Stable Group; n = 328) or reporting a significant increase in symptomatology between BC diagnosis and 12 months later (Deteriorated Group; n = 50). Sociodemographic, life-style, psychosocial, and medical variables collected on the first visit to their oncologist and three months later served as potential predictors of patient risk stratification. The flexible and comprehensive machine learning (ML) pipeline used entailed feature selection, model training, validation and testing. Model-agnostic analyses aided interpretation of model results at the variable- and patient-level. The two groups were discriminated with a high degree of accuracy (Area Under the Curve = 0.864) and a fair balance of sensitivity (0.85) and specificity (0.87). Both psychological (negative affect, certain coping with cancer reactions, lack of sense of control/positive expectations, and difficulties in regulating negative emotions) and biological variables (baseline percentage of neutrophils, thrombocyte count) emerged as important predictors of mental health deterioration in the long run. Personalized break-down profiles revealed the relative impact of specific variables toward successful model predictions for each patient. Identifying key risk factors for mental health deterioration is an essential first step toward prevention. Supervised ML models may guide clinical recommendations toward successful illness adaptation.

The relative proportion of comorbidities among rhinitis and rhinosinusitis patients and their impact on visit burden.

Background: The aim was to evaluate the relative proportion of Non-steroidal anti-inflammatory drug exacerbated respiratory disease (NERD) and other comorbidities, and their impact on the burden of outpatient visits due to allergic rhinitis (AR), non-allergic rhinitis (NAR), acute rhinosinusitis (ARS), and chronic rhinosinusitis with nasal polyps (CRSwNP) and without (CRSsNP). Methods: We used hospital registry data of a random sample of 5080 rhinitis/rhinosinusitis patients diagnosed during 2005-2019. International Statistical Classification of Diseases and Related Health Problems (ICD10) diagnoses, visits, and other factors were collected from electronic health records by using information extraction and data processing methods. Cox's proportional hazards model was used for modeling the time to the next outpatient visit. Results: The mean (±standard deviation) age of the population was 33.6 (±20.7) years and 56.1% were female. The relative proportion of AR, NAR, ARS, CRSsNP and CRSwNP, were 33.5%, 27.5%, 27.2%, 20.7%, and 10.9%, respectively. The most common other comorbidities were asthma (44.4%), other chronic respiratory diseases (38.5%), musculoskeletal diseases (38.4%), and cardiovascular diseases (35.7%). Non-steroidal anti-inflammatory drug exacerbated respiratory disease existed in 3.9% of all patients, and 17.7% of the CRSwNP group. The relative proportion of subjects having 1, 2, 3 and ≥ 4 other diseases were 18.0%, 17.6%, 17.0%, 37.0%, respectively. All diseases except AR, ARS, and mouth breathing, were associated with a high frequency of outpatient visits. Conclusions: Our results revealed a high relative proportion of NERD and other comorbidities, which affect the burden of outpatient visits and hence confirm the socioeconomic impact of upper airway diseases.

Using machine learning for the personalised prediction of revision endoscopic sinus surgery.

BACKGROUND: Revision endoscopic sinus surgery (ESS) is often considered for chronic rhinosinusitis (CRS) if maximal conservative treatment and baseline ESS prove insufficient. Emerging research outlines the risk factors of revision ESS. However, accurately predicting revision ESS at the individual level remains uncertain. This study aims to examine the prediction accuracy of revision ESS and to identify the effects of risk factors at the individual level. METHODS: We collected demographic and clinical variables from the electronic health records of 767 surgical CRS patients ≥16 years of age. Revision ESS was performed on 111 (14.5%) patients. The prediction accuracy of revision ESS was examined by training and validating different machine learning models, while the effects of variables were analysed using the Shapley values and partial dependence plots. RESULTS: The logistic regression, gradient boosting and random forest classifiers performed similarly in predicting revision ESS. Area under the receiving operating characteristic curve (AUROC) values were 0.744, 0.741 and 0.730, respectively, using data collected from the baseline visit until six months after baseline ESS. The length of time during which data were collected improved the prediction performance. For data collection times of 0, 3, 6 and 12 months after baseline ESS, AUROC values for the logistic regression were 0.682, 0.715, 0.744 and 0.784, respectively. The number of visits before or after baseline ESS, the number of days from the baseline visit to the baseline ESS, patient age, CRS with nasal polyps (CRSwNP), asthma, non-steroidal anti-inflammatory drug exacerbated respiratory disease and immunodeficiency or suspicion of it all associated with revision ESS. Patient age and number of visits before baseline ESS carried non-linear effects for predictions. CONCLUSIONS: Intelligent data analysis identified important predictors of revision ESS at the individual level, such as the frequency of clinical visits, patient age, Type 2 high diseases and immunodeficiency or a suspicion of it.

Eosinophilia, asthma, NERD and the use of oral corticosteroids predict uncontrolled chronic rhinosinusitis with nasal polyps after surgery.

BACKGROUND: Severe uncontrolled chronic rhinosinusitis with nasal polyps (CRSwNP) is a challenging condition to treat. The European Position Paper on Rhinosinusitis and Nasal Polyps 2020 (EPOS2020) has the following criteria when considering biological therapy for severe uncontrolled CRSwNP: eosinophilia, need for oral corticosteroids (OCS), symptom score, loss of sense of smell and co-morbid asthma. OBJECTIVE: This study aimed at finding associations of baseline factors with uncontrolled CRSwNP after endoscopic sinus surgery (ESS). METHODS: Electronic health record data of CRSwNP patients (N = 137) undergoing ESS in 2002-17 were used. Endpoints of uncontrolled CRSwNP were revision ESS, purchased OCS and antibiotic courses during follow up. Baseline factors were chosen based on EPOS2020 and the data available: nasal polyp (NP) eosinophilia, peripheral blood eosinophilia, co-existing asthma and/or non-steroidal anti-inflammatory drug exacerbated respiratory disease (NERD), need for OCS during the previous year, previous ESS, endoscopic NP score, and Lund-Mackay score of sinus computed tomography scans. RESULTS: During the follow-up of 10.1 ± 3.1 (mean ± standard deviation) years, 35 (25.5%) individuals underwent revision ESS. The best predictive model was obtained by a sum of baseline (1) blood eosinophilia ≥ 250 cells/≥l and/or NP eosinophilia ≥ 30% (Eos), (2) asthma/NERD, and (3) ≥ 1 OCS/year. It was significantly associated with revision ESS, purchased doctor-prescribed OCS and antibiotic courses during follow-up. CONCLUSIONS: We identified similar predictive variables for uncontrolled CRSwNP that are used in the EPOS2020 indications of biological therapy, thus suggesting that these estimates are usable in clinical practice.